Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4018 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3014. Min Range: -8.3014
Max Act: 8.2389. Min Act: -0.1700
Data Index: 6373259 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3014. Min Range: -8.3014
Max Act: 8.3014. Min Act: -0.1700
Data Index: 1642476 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3014. Min Range: -8.3014
Max Act: 8.1764. Min Act: -0.1700
Data Index: 183616 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3014. Min Range: -8.3014
Max Act: 8.0514. Min Act: -0.1700
Data Index: 2117905 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3014. Min Range: -8.3014
Max Act: 8.0514. Min Act: -0.1700
Data Index: 4533080 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3014. Min Range: -8.3014
Max Act: 7.9264. Min Act: -0.1700
Data Index: 6753735 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3014. Min Range: -8.3014
Max Act: 7.9264. Min Act: -0.1700
Data Index: 2978732 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3014. Min Range: -8.3014
Max Act: 7.9264. Min Act: -0.1700
Data Index: 3096312 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3014. Min Range: -8.3014
Max Act: 7.8639. Min Act: -0.1700
Data Index: 4856368 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3014. Min Range: -8.3014
Max Act: 7.8639. Min Act: -0.1700
Data Index: 1073540 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3014. Min Range: -8.3014
Max Act: 7.8639. Min Act: -0.1700
Data Index: 2117907 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3014. Min Range: -8.3014
Max Act: 7.8014. Min Act: -0.1700
Data Index: 1880246 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3014. Min Range: -8.3014
Max Act: 7.8014. Min Act: -0.1700
Data Index: 736421 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3014. Min Range: -8.3014
Max Act: 7.7701. Min Act: -0.1700
Data Index: 45275 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3014. Min Range: -8.3014
Max Act: 7.7701. Min Act: -0.1700
Data Index: 3563619 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3014. Min Range: -8.3014
Max Act: 7.7701. Min Act: -0.1700
Data Index: 7737585 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3014. Min Range: -8.3014
Max Act: 7.7389. Min Act: -0.1700
Data Index: 7975322 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3014. Min Range: -8.3014
Max Act: 7.7389. Min Act: -0.1700
Data Index: 5451929 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3014. Min Range: -8.3014
Max Act: 7.7389. Min Act: -0.1700
Data Index: 5978281 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3014. Min Range: -8.3014
Max Act: 7.7076. Min Act: -0.1700
Data Index: 7356314 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #19